输出统计数与文本内容

查找重复行操作

// Copyright © 2016 Alan A. A. Donovan & Brian W. Kernighan.
// License: https://creativecommons.org/licenses/by-nc-sa/4.0/

// See page 8.
//!+

// Dup1 prints the text of each line that appears more than
// once in the standard input, preceded by its count.
package main

import (
    "bufio"
    "fmt"
    "os"
)

func main() {
    counts := make(map[string]int)
    input := bufio.NewScanner(os.Stdin)
    for input.Scan() {
        counts[input.Text()]++
    }
    // NOTE: ignoring potential errors from input.Err()
    for line, n := range counts {
        if n > 1 {
            fmt.Printf("%d\t%s\n", n, line)
        }
    }
}

//!-

---------------------------------------------------------------------------

// ch1 project main.go
package main

import (
    "bufio"
    "bytes"
    "fmt"
    "log"
    "os"
)

var (
    buf    bytes.Buffer
    logger = log.New(&buf, "INFO: ", log.Lshortfile)
)

func info_log(info string) {
    logger.Output(2, info)
    fmt.Print(&buf)
}

func main() {
    var f *os.File
    var err error
    if len(os.Args) < 2 {
        info_log("args err")
        os.Exit(-1)
    }
    f, err = os.Open(os.Args[1])
    if err != nil {
        info_log("open file error")
        os.Exit(-1)
    }

    input := bufio.NewScanner(f)
    var counter = make(map[string]int)
    for input.Scan() {
        counter[input.Text()]++
    }

    for text, n := range counter {
        fmt.Printf("%d: %s\n", n, text)
    }

}

结果输出：
[root@hadoop1 ch1]# ./echo_my aa.txt 
2: hello world
1: good idea
1: this is good
1: hello world this is
[root@hadoop1 ch1]#
---------------------------------------------------------------------------

package main

import (
    "bufio"
    "fmt"
    "os"
)

func main() {
    counts := make(map[string]int)
    files := os.Args[1:]
    if len(files) == 0 {
        countLines(os.Stdin, counts)
    } else {
        for _, arg := range files {
            f, err := os.Open(arg)
            if err != nil {
                fmt.Fprintf(os.Stderr, "dup2: %v\n", err)
                continue
            }
            countLines(f, counts)
            f.Close()
        }
    }
    for line, n := range counts {
        if n > 1 {
            fmt.Printf("%d\t%s\n", n, line)
        }
    }
}

func countLines(f *os.File, counts map[string]int) {
    input := bufio.NewScanner(f)
    for input.Scan() {
        counts[input.Text()]++
    }
    // NOTE: ignoring potential errors from input.Err()
}

//!-

结果输出：
[root@hadoop1 ch1]# ./echo_my aa.txt 
2 hello world
[root@hadoop1 ch1]#
--------------------------------------------------------------------------------

package main

import (
    "fmt"
    "io/ioutil"
    "os"
    "strings"
)

func main() {
    counts := make(map[string]int)
    for _, filename := range os.Args[1:] {
        data, err := ioutil.ReadFile(filename)
        if err != nil {
            fmt.Fprintf(os.Stderr, "dup3: %v\n", err)
            continue
        }
        for _, line := range strings.Split(string(data), "\n") {
            counts[line]++
        }
    }
    for line, n := range counts {
        if n > 1 {
            fmt.Printf("%d\t%s\n", n, line)
        }
    }
}

//!-

输出结果：
[root@hadoop1 ch1]# ./echo_my aa.txt 
2 hello world
[root@hadoop1 ch1]#